Conversation processing method and apparatus based on artificial intelligence, device and computer-readable storage medium
A conversation processing method and apparatus based on artificial intelligence, a device and a computer-readable storage medium. The disclosure embodiments, enable the user feedback information provided by conversation service conducted by the user to model conversation understanding system, then according to the user feedback information, perform adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system so that it is possible to execute the conversation service with the model conversation understanding system, based on the adjustment state. Since a fault-tolerant and fault-correcting mechanism is provided, it is possible to adjust the understanding capability of the model conversation understanding system in real time and thereby effectively improve the reliability of conversation by collecting the user's user feedback information, and then adjusting the service state of the model conversation understanding system in time based on the user feedback information.
1. A conversation processing method based on artificial intelligence, wherein the method comprises:
obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system;
according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and
using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system,
wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and
wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises:
obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system;
according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and
performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system,
wherein the adjustment processing for a service state of the basic conversation understanding system comprises:
for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
2. The method according to claim 1 , wherein the user feedback information comprises at least one of the following information:
positive information;
negative information;
error-correcting information;
clarifying information; and
defining information.
3. The method according to claim 1 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions;
according to the application scenario information, building the basic conversation understanding system having basic service logic.
4. The method according to claim 1 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining evaluation data of the basic conversation understanding system according to the training feedback information;
obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
5. The method according to claim 1 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises:
performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.
6. A device, wherein the device comprises:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by said one or more processors, enable said one or more processors to implement a conversation processing method based on artificial intelligence, wherein the method comprises:
obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system;
according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and
using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system,
wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and
wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises:
obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system;
according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and
performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system, wherein the adjustment processing for a service state of the basic conversation understanding system comprises.
for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
7. The device according to claim 6 , wherein the user feedback information comprises at least one of the following information:
positive information;
negative information;
error-correcting information;
clarifying information; and
defining information.
8. The device according to claim 6 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions;
according to the application scenario information, building the basic conversation understanding system having basic service logic.
9. The device according to claim 6 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining evaluation data of the basic conversation understanding system according to the training feedback information;
obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
10. The device according to claim 6 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises:
performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.
11. A non-transitory computer readable storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a conversation processing method based on artificial intelligence, wherein the method comprises:
obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system;
according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system; and
using the model conversation understanding system to execute the conversation service based on the adjustment state of the model conversation understanding system,
wherein the user feedback information comprises active feedback information and passive feedback information, the active feedback information comprising a newly-added intent, parameter, execution action and a triggering rule of the execution action; and
wherein before obtaining user feedback information provided by conversation service conducted by a user and a model conversation understanding system, the method further comprises:
obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system;
according to the training feedback information, performing adjustment processing for a service state of the basic conversation understanding system, to obtain an adjustment state of the basic conversation understanding system; and
performing data merging processing according to the training feedback information and the adjustment state of the basic conversation understanding system, to obtain model training data for building the model conversation understanding system, wherein the adjustment processing for a service state of the basic conversation understanding system comprises:
for the active feedback information, correction of a speech recognition result; correction of an intent recognition result; correction or supplement of parameter types and parameter values; correction or supplement of an execution result; confirmation or negation of a speech recognition result; an intent recognition result, parameters and an execution result; and a certain newly-added intent, parameter, execution action and a triggering rule of the execution action; and for the passive feedback information, a query for the speech recognition result; a query for the intent recognition result; a query for the parameter type or parameter value; a query for the execution result; and a query for missing data.
12. The non-transitory computer readable storage medium according to claim 11 , wherein the user feedback information comprises at least one of the following information:
positive information;
negative information;
error-correcting information;
clarifying information; and
defining information.
13. The non-transitory computer readable storage medium according to claim 11 , wherein before obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining application scenario information of a conversation service scenario provided by a developer, the application scenario information including intent information, parameter information and corresponding execution actions;
according to the application scenario information, building the basic conversation understanding system having basic service logic.
14. The non-transitory computer readable storage medium according to claim 11 , wherein after obtaining training feedback information provided by conversation service conducted by a user and a basic conversation understanding system, the method further comprises:
obtaining evaluation data of the basic conversation understanding system according to the training feedback information;
obtaining a satisfaction degree index of the basic conversation understanding system according to the evaluation data.
15. The non-transitory computer readable storage medium according to claim 11 , wherein after the step of, according to the user feedback information, performing adjustment processing for a service state of the model conversation understanding system, to obtain an adjustment state of the model conversation understanding system, the method further comprises:
performing data merging processing according to the user feedback information and the adjustment state of the model conversation understanding system, to obtain updated training data for updating the model conversation understanding system.